© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14276
    Prev
    Next
    INDEX
    Explanations

    sentences expressing approval and positive sentiment, often using intensifiers and adverbs.

    oai_token-act-pair · gemini-2.0-flash

    does

    np_max-act-logits · gemini-2.0-flash

    say "degree/quality modifiers" Method used: 2 — tokens are degree/quality modifiers — say "degree/quality modifiers"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     well
    -1.71
    Well
    -1.66
     Well
    -1.65
    well
    -1.59
     WELL
    -1.38
    WELL
    -1.32
     bien
    -1.29
    wells
    -0.98
     hyvin
    -0.87
    Bien
    -0.84
    POSITIVE LOGITS
    jelen
    0.54
     menac
    0.53
    gling
    0.49
    çons
    0.47
    mistry
    0.46
     Marcelo
    0.45
    Сюжет
    0.45
    
    0.45
    udios
    0.45
    gesterone
    0.45
    Activations Density 10.289%

    No Known Activations